Tag
This study audits demographic leakage in German LLM-generated resumes, finding that despite anonymization, classifiers can reliably distinguish between male and female names due to subtle linguistic differences, raising fairness concerns in AI hiring pipelines.
This research investigates whether removing language fields from de-identified résumés prevents demographic leakage in LLM bias audits, finding that non-language prose still allows inference and that evaluation design significantly affects outcomes.